djuna
/

TEST3-Q2.5-Lenned-14B

@@ -1,101 +1,114 @@
----
-base_model:
-- Krystalan/DRT-o1-14B
-- huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
-- djuna/Q2.5-Veltha-14B-0.5
-- Qwen/Qwen2.5-14B
-- netease-youdao/Confucius-o1-14B
-library_name: transformers
-tags:
-- mergekit
-- merge
----
-# merge
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-## Merge Details
-### Merge Method
-This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
-### Models Merged
-The following models were included in the merge:
-* [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B)
-* [huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated)
-* [djuna/Q2.5-Veltha-14B-0.5](https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5)
-* [netease-youdao/Confucius-o1-14B](https://huggingface.co/netease-youdao/Confucius-o1-14B)
-### Configuration
-The following YAML configuration was used to produce this model:
-```yaml
-models:
-  - model: Qwen/Qwen2.5-14B
-  - model: netease-youdao/Confucius-o1-14B
-  - model: djuna/Q2.5-Veltha-14B-0.5
-  - model: Krystalan/DRT-o1-14B
-  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
-    parameters:
-      select_topk: 0.5
-merge_method: sce
-base_model: Qwen/Qwen2.5-14B
-tokenizer:
-  source: "djuna/Q2.5-Veltha-14B-0.5"
-  tokens:
-    <|endoftext|>:
-      source: "djuna/Q2.5-Veltha-14B-0.5"
-    <|im_start|>:
-      source: "djuna/Q2.5-Veltha-14B-0.5"
-    <|im_end|>:
-      source: "djuna/Q2.5-Veltha-14B-0.5"
-    <|object_ref_start|>:
-      source: "djuna/Q2.5-Veltha-14B-0.5"
-    <|object_ref_end|>:
-      source: "djuna/Q2.5-Veltha-14B-0.5"
-    <|box_start|>:
-      source: "djuna/Q2.5-Veltha-14B-0.5"
-    <|box_end|>:
-      source: "djuna/Q2.5-Veltha-14B-0.5"
-    <｜end▁of▁sentence｜>:
-      source:
-        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
-        kind: "model_token"
-        token: "<｜end▁of▁sentence｜>"
-    <｜User｜>:
-      source:
-        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
-        kind: "model_token"
-        token: "<｜User｜>"
-    <｜Assistant｜>:
-      source:
-        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
-        kind: "model_token"
-        token: "<｜Assistant｜>"
-    <｜begin▁of▁sentence｜>:
-      source:
-        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
-        kind: "model_token"
-        token: "<｜begin▁of▁sentence｜>"
-    <|EOT|>:
-      source:
-        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
-        kind: "model_token"
-        token: "<|EOT|>"
-    <think>:
-      source:
-        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
-        kind: "model_token"
-        token: "<think>"
-    </think>:
-      source:
-        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
-        kind: "model_token"
-        token: "</think>"
-dtype: float32
-out_dtype: bfloat16
-```

+---
+base_model:
+- Krystalan/DRT-o1-14B
+- huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
+- djuna/Q2.5-Veltha-14B-0.5
+- Qwen/Qwen2.5-14B
+- netease-youdao/Confucius-o1-14B
+library_name: transformers
+tags:
+- mergekit
+- merge
+language:
+- zho
+- eng
+- fra
+- spa
+- por
+- deu
+- ita
+- rus
+- jpn
+- kor
+- vie
+- tha
+- ara
+---
+# merge
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+## Merge Details
+### Merge Method
+This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
+### Models Merged
+The following models were included in the merge:
+* [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B)
+* [huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated)
+* [djuna/Q2.5-Veltha-14B-0.5](https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5)
+* [netease-youdao/Confucius-o1-14B](https://huggingface.co/netease-youdao/Confucius-o1-14B)
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+models:
+  - model: Qwen/Qwen2.5-14B
+  - model: netease-youdao/Confucius-o1-14B
+  - model: djuna/Q2.5-Veltha-14B-0.5
+  - model: Krystalan/DRT-o1-14B
+  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
+    parameters:
+      select_topk: 0.5
+merge_method: sce
+base_model: Qwen/Qwen2.5-14B
+tokenizer:
+  source: "djuna/Q2.5-Veltha-14B-0.5"
+  tokens:
+    <|endoftext|>:
+      source: "djuna/Q2.5-Veltha-14B-0.5"
+    <|im_start|>:
+      source: "djuna/Q2.5-Veltha-14B-0.5"
+    <|im_end|>:
+      source: "djuna/Q2.5-Veltha-14B-0.5"
+    <|object_ref_start|>:
+      source: "djuna/Q2.5-Veltha-14B-0.5"
+    <|object_ref_end|>:
+      source: "djuna/Q2.5-Veltha-14B-0.5"
+    <|box_start|>:
+      source: "djuna/Q2.5-Veltha-14B-0.5"
+    <|box_end|>:
+      source: "djuna/Q2.5-Veltha-14B-0.5"
+    <｜end▁of▁sentence｜>:
+      source:
+        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
+        kind: "model_token"
+        token: "<｜end▁of▁sentence｜>"
+    <｜User｜>:
+      source:
+        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
+        kind: "model_token"
+        token: "<｜User｜>"
+    <｜Assistant｜>:
+      source:
+        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
+        kind: "model_token"
+        token: "<｜Assistant｜>"
+    <｜begin▁of▁sentence｜>:
+      source:
+        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
+        kind: "model_token"
+        token: "<｜begin▁of▁sentence｜>"
+    <|EOT|>:
+      source:
+        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
+        kind: "model_token"
+        token: "<|EOT|>"
+    <think>:
+      source:
+        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
+        kind: "model_token"
+        token: "<think>"
+    </think>:
+      source:
+        model: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
+        kind: "model_token"
+        token: "</think>"
+dtype: float32
+out_dtype: bfloat16
+```